Doc-String Prediction on Doc-String
0.12Last-Token KL DivergenceFAP
Evaluation Results
| Method | Links | |
|---|---|---|
| FAPModel=Gemma-2-2B, Budget (K)=8002026.04 | 0.12 | |
| FAP-SynergyModel=Gemma-2-2B, Budget (K)=8002026.04 | 0.12 | |
| FAPModel=Llama-3.2-1B, Budget (K)=8002026.04 | 0.14 | |
| FAP-SynergyModel=Llama-3.2-1B, Budget (K)=8002026.04 | 0.14 | |
| FAPModel=Gemma-2-2B, Budget (K)=4002026.04 | 0.21 | |
| FAP-SynergyModel=Gemma-2-2B, Budget (K)=4002026.04 | 0.21 | |
| FAP-SynergyModel=Gemma-2-2B, Budget (K)=2002026.04 | 0.29 | |
| FAPModel=Gemma-2-2B, Budget (K)=2002026.04 | 0.3 | |
| FAPModel=Llama-3.2-1B, Budget (K)=4002026.04 | 0.32 | |
| FAP-SynergyModel=Llama-3.2-1B, Budget (K)=4002026.04 | 0.32 | |
| FAPModel=Gemma-2-2B, Budget (K)=1002026.04 | 0.36 | |
| FAP-SynergyModel=Gemma-2-2B, Budget (K)=1002026.04 | 0.36 | |
| Activation-MagnitudeModel=Gemma-2-2B, Budget (K)=8002026.04 | 0.36 | |
| ACDC-Style PruningModel=Gemma-2-2B, Budget (K)=8002026.04 | 0.36 | |
| ACDC-Style PruningModel=Gemma-2-2B, Budget (K)=4002026.04 | 0.38 | |
| ACDC-Style PruningModel=Gemma-2-2B, Budget (K)=2002026.04 | 0.39 | |
| FAP-SynergyModel=Gemma-2-2B, Budget (K)=502026.04 | 0.4 | |
| Activation-MagnitudeModel=Gemma-2-2B, Budget (K)=4002026.04 | 0.4 | |
| ACDC-Style PruningModel=Gemma-2-2B, Budget (K)=502026.04 | 0.4 | |
| ACDC-Style PruningModel=Gemma-2-2B, Budget (K)=1002026.04 | 0.4 | |
| FAPModel=Gemma-2-2B, Budget (K)=502026.04 | 0.41 | |
| Activation-MagnitudeModel=Gemma-2-2B, Budget (K)=1002026.04 | 0.42 | |
| Activation-MagnitudeModel=Gemma-2-2B, Budget (K)=2002026.04 | 0.42 | |
| Activation-MagnitudeModel=Gemma-2-2B, Budget (K)=502026.04 | 0.43 | |
| FAPModel=Llama-3.2-1B, Budget (K)=2002026.04 | 0.53 | |
| FAP-SynergyModel=Llama-3.2-1B, Budget (K)=2002026.04 | 0.53 | |
| FAP-SynergyModel=Llama-3.2-1B, Budget (K)=1002026.04 | 0.68 | |
| Activation-MagnitudeModel=Llama-3.2-1B, Budget (K)=8002026.04 | 0.68 | |
| FAPModel=Llama-3.2-1B, Budget (K)=1002026.04 | 0.69 | |
| FAP-SynergyModel=Llama-3.2-1B, Budget (K)=502026.04 | 0.74 | |
| ACDC-Style PruningModel=Llama-3.2-1B, Budget (K)=8002026.04 | 0.74 | |
| ACDC-Style PruningModel=Llama-3.2-1B, Budget (K)=4002026.04 | 0.75 | |
| ACDC-Style PruningModel=Llama-3.2-1B, Budget (K)=1002026.04 | 0.76 | |
| ACDC-Style PruningModel=Llama-3.2-1B, Budget (K)=2002026.04 | 0.76 | |
| Activation-MagnitudeModel=Llama-3.2-1B, Budget (K)=4002026.04 | 0.77 | |
| FAPModel=Llama-3.2-1B, Budget (K)=502026.04 | 0.78 | |
| ACDC-Style PruningModel=Llama-3.2-1B, Budget (K)=502026.04 | 0.78 | |
| Activation-MagnitudeModel=Llama-3.2-1B, Budget (K)=2002026.04 | 0.85 | |
| Activation-MagnitudeModel=Llama-3.2-1B, Budget (K)=502026.04 | 0.88 | |
| Activation-MagnitudeModel=Llama-3.2-1B, Budget (K)=1002026.04 | 0.88 |